ó
ÄqPc @ s¹ d Z d d l m Z d d l m Z d d l m Z d d l m Z m
Z
m Z y
e Z
Wn e k
r{ e e f Z
n Xy d d l m Z Wn! e k
r³ d d l m Z n Xy d d l m Z Wn! e k
rë d d l m Z n Xd e f d „ ƒ YZ y d d
l m Z Wn e k
r)n Xd e f d „ ƒ YZ e ƒ Z d
„ Z e d d „ Z e e d d „ Z e e d d „ Z e d d „ Z! e d d „ Z" d „ Z# e ƒ Z$ d S( s?
An interface to html5lib that mimics the lxml.html interface.
iÿÿÿÿ( t
HTMLParser( t TreeBuilder( t etree( t _contains_block_level_tagt XHTML_NAMESPACEt Element( t urlopen( t urlparseR c B s e Z d Z e d „ Z RS( s* An html5lib HTML parser with lxml as tree.c K s t j | d | d t | d S( Nt strictt tree( t _HTMLParsert __init__R ( t selfR t kwargs( ( s; /usr/lib64/python2.7/site-packages/lxml/html/html5parser.pyR s ( t __name__t
__module__t __doc__t FalseR ( ( ( s; /usr/lib64/python2.7/site-packages/lxml/html/html5parser.pyR s ( t XHTMLParserR c B s e Z d Z e d „ Z RS( s+ An html5lib XHTML Parser with lxml as tree.c K s t j | d | d t | d S( NR R ( t _XHTMLParserR R ( R R R
( ( s; /usr/lib64/python2.7/site-packages/lxml/html/html5parser.pyR ( s ( R R R R R ( ( ( s; /usr/lib64/python2.7/site-packages/lxml/html/html5parser.pyR % s c C s6 | j | ƒ } | d k r | S| j d t | f ƒ S( Ns {%s}%s( t findt NoneR ( R t tagt elem( ( s; /usr/lib64/python2.7/site-packages/lxml/html/html5parser.pyt _find_tag. s c C sL t | t ƒ s t d ƒ ‚ n | d k r3 t } n | j | d | ƒj ƒ S( s% Parse a whole document into a string.s string requiredt
useChardetN( t
isinstancet _stringst TypeErrorR t html_parsert parset getroot( t htmlt
guess_charsett parser( ( s; /usr/lib64/python2.7/site-packages/lxml/html/html5parser.pyt document_fromstring5 s
c C s¥ t | t ƒ s t d ƒ ‚ n | d k r3 t } n | j | d d | ƒ} | r¡ t | d t ƒ r¡ | r¡ | d j ƒ r” t j d | d ƒ ‚ n | d =q¡ n | S( s” Parses several HTML elements, returning a list of elements.
The first item in the list may be a string. If no_leading_text is true,
then it will be an error if there is leading text, and it will always be
a list of only elements.
If `guess_charset` is `True` and the text was not unicode but a
bytestring, the `chardet` library will perform charset guessing on the
string.
s string requiredt divR i s There is leading text: %rN( R R R R R t
parseFragmentt stripR t ParserError( R t no_leading_textR! R" t children( ( s; /usr/lib64/python2.7/site-packages/lxml/html/html5parser.pyt fragments_fromstring@ s
c C s; t | t ƒ s t d ƒ ‚ n t | ƒ } t | d | d | d | ƒ} | r· t | t ƒ sg d } n t | ƒ } | r³ t | d t ƒ r£ | d | _ | d =n | j | ƒ n | S| sÏ t j d ƒ ‚ n t
| ƒ d k ró t j d ƒ ‚ n | d } | j r.| j j ƒ r.t j d
| j ƒ ‚ n d | _ | S( sX Parses a single HTML element; it is an error if there is more than
one element, or if anything but whitespace precedes or follows the
element.
If create_parent is true (or is a tag name) then a parent node
will be created to encapsulate the HTML in a single element. In
this case, leading or trailing text is allowed.
s string requiredR! R" R( R$ i s No elements foundi s Multiple elements founds Element followed by text: %rN( R R R t boolR* R t textt extendR R' t lent tailR& R ( R t
create_parentR! R" t accept_leading_textt elementst new_roott result( ( s; /usr/lib64/python2.7/site-packages/lxml/html/html5parser.pyt fragment_fromstring\ s2
c C s t | t ƒ s t d ƒ ‚ n t | d | d | ƒ} | d j ƒ j ƒ } | j d ƒ sj | j d ƒ rn | St | d ƒ } t | ƒ r | St | d ƒ } t | ƒ d k rò | j sÈ | j j
ƒ rò | d
j sê | d
j j
ƒ rò | d St | ƒ r
d | _
n d
| _
| S( sü Parse the html, returning a single element/document.
This tries to minimally parse the chunk of text, without knowing if it
is a fragment or a document.
base_url will set the document's base_url attribute (and the tree's docinfo.URL)
s string requiredR" R! i2 s <htmls <!doctypet headt bodyi iÿÿÿÿi R$ t span( R R R R# t lstript lowert
startswithR R. R, R& R/ R R ( R R! R" t doct startR6 R7 ( ( s; /usr/lib64/python2.7/site-packages/lxml/html/html5parser.pyt
fromstring… s$ ," c C sj | d k r t } n t | t ƒ s- | } n* t | ƒ rH t | ƒ } n t | d ƒ } | j | d | ƒS( s· Parse a filename, URL, or file-like object into an HTML document
tree. Note: this returns a tree, not an element. Use
``parse(...).getroot()`` to get the document root.
t rbR N( R R R R t _looks_like_urlR t openR ( t filename_url_or_fileR! R" t fp( ( s; /usr/lib64/python2.7/site-packages/lxml/html/html5parser.pyR ¯ s c C s t | ƒ d } | d k S( Ni t ( R ( t strt scheme( ( s; /usr/lib64/python2.7/site-packages/lxml/html/html5parser.pyR@ ¾ s N(% R t html5libR R
t html5lib.treebuilders.etree_lxmlR t lxmlR t lxml.htmlR R R t
basestringR t NameErrort bytesRE t urllib2R t ImportErrort urllib.requestR t urllib.parseR R t xhtml_parserR t TrueR R# R R* R5 R> R R@ R ( ( ( s; /usr/lib64/python2.7/site-packages/lxml/html/html5parser.pyt <module> sB
(*